Universidad Peruana Cayetano Heredia

How to tune the RBF SVM hyperparameters? An empirical evaluation of 18 search algorithms

Mostrar el registro sencillo del ítem

dc.contributor.author Wainer, Jacques
dc.contributor.author Fonseca, Pablo
dc.date.accessioned 2021-10-04T23:00:58Z
dc.date.available 2021-10-04T23:00:58Z
dc.date.issued 2021
dc.identifier.uri https://hdl.handle.net/20.500.12866/9838
dc.description.abstract SVM with an RBF kernel is usually one of the best classification algorithms for most data sets, but it is important to tune the two hyperparameters C and γ to the data itself. In general, the selection of the hyperparameters is a non-convex optimization problem and thus many algorithms have been proposed to solve it, among them: grid search, random search, Bayesian optimization, simulated annealing, particle swarm optimization, Nelder Mead, and others. There have also been proposals to decouple the selection of γ and C. We empirically compare 18 of these proposed search algorithms (with different parameterizations for a total of 47 combinations) on 115 real-life binary data sets. We find (among other things) that trees of Parzen estimators and particle swarm optimization select better hyperparameters with only a slight increase in computation time with respect to a grid search with the same number of evaluations. We also find that spending too much computational effort searching the hyperparameters will not likely result in better performance for future data and that there are no significant differences among the different procedures to select the best set of hyperparameters when more than one is found by the search algorithms en_US
dc.language.iso eng
dc.publisher Springer
dc.relation.ispartofseries Artificial Intelligence Review
dc.rights info:eu-repo/semantics/restrictedAccess
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
dc.subject Bayesian optimization en_US
dc.subject Classification (of information) en_US
dc.subject Classification algorithm en_US
dc.subject Computation time en_US
dc.subject Computational effort en_US
dc.subject Convex optimization en_US
dc.subject Empirical evaluations en_US
dc.subject Grid search en_US
dc.subject Hyperparameters en_US
dc.subject Learning algorithms en_US
dc.subject Non-convex optimization algorithms en_US
dc.subject Nonconvex optimization en_US
dc.subject Particle swarm optimization (PSO) en_US
dc.subject Parzen estimators en_US
dc.subject Random search en_US
dc.subject Search Algorithms en_US
dc.subject Simulated annealing en_US
dc.subject Support vector machines en_US
dc.subject SVM en_US
dc.title How to tune the RBF SVM hyperparameters? An empirical evaluation of 18 search algorithms en_US
dc.type info:eu-repo/semantics/article
dc.identifier.doi https://doi.org/10.1007/s10462-021-10011-5
dc.subject.ocde https://purl.org/pe-repo/ocde/ford#1.02.00
dc.relation.issn 1573-7462


Ficheros en el ítem

Ficheros Tamaño Formato Ver

No hay ficheros asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

info:eu-repo/semantics/restrictedAccess Excepto si se señala otra cosa, la licencia del ítem se describe como info:eu-repo/semantics/restrictedAccess

Buscar en el Repositorio


Listar

Panel de Control

Estadísticas